English
Related papers

Related papers: Centered Self-Attention Layers

200 papers

Transformers have demonstrated remarkable performance across diverse domains. The key component of Transformers is self-attention, which learns the relationship between any two tokens in the input sequence. Recent studies have revealed that…

Machine Learning · Computer Science 2025-05-14 Hyowon Wi , Jeongwhan Choi , Noseong Park

It has been discovered that Graph Convolutional Networks (GCNs) encounter a remarkable drop in performance when multiple layers are piled up. The main factor that accounts for why deep GCNs fail lies in over-smoothing, which isolates the…

Machine Learning · Computer Science 2023-06-22 Jiaqi Han , Wenbing Huang , Yu Rong , Tingyang Xu , Fuchun Sun , Junzhou Huang

Overparameterized networks trained to convergence have shown impressive performance in domains such as computer vision and natural language processing. Pushing state of the art on salient tasks within these domains corresponds to these…

Machine Learning · Computer Science 2020-08-04 James O' Neill

Deep imitation learning is promising for solving dexterous manipulation tasks because it does not require an environment model and pre-programmed robot behavior. However, its application to dual-arm manipulation tasks remains challenging.…

Robotics · Computer Science 2025-05-23 Heecheol Kim , Yoshiyuki Ohmura , Yasuo Kuniyoshi

The ability of deep neural networks to generalize well in the overparameterized regime has become a subject of significant research interest. We show that overparameterized autoencoders exhibit memorization, a form of inductive bias that…

Computer Vision and Pattern Recognition · Computer Science 2019-09-05 Adityanarayanan Radhakrishnan , Karren Yang , Mikhail Belkin , Caroline Uhler

Recently, transformer architectures for graphs emerged as an alternative to established techniques for machine learning with graphs, such as (message-passing) graph neural networks. So far, they have shown promising empirical results, e.g.,…

Machine Learning · Computer Science 2024-04-01 Luis Müller , Mikhail Galkin , Christopher Morris , Ladislav Rampášek

Curvature notions on graphs provide a theoretical description of graph topology, highlighting bottlenecks and denser connected regions. Artifacts of the message passing paradigm in Graph Neural Networks, such as oversmoothing and…

Machine Learning · Computer Science 2026-02-25 Floriano Tori , Lorenzo Bini , Marco Sorbi , Stéphane Marchand-Maillet , Vincent Ginis

Transformers are extremely successful machine learning models whose mathematical properties remain poorly understood. Here, we rigorously characterize the behavior of transformers with hardmax self-attention and normalization sublayers as…

Computation and Language · Computer Science 2026-05-14 Albert Alcalde , Giovanni Fantuzzi , Enrique Zuazua

Recommendation models utilizing Graph Convolutional Networks (GCNs) have achieved state-of-the-art performance, as they can integrate both the node information and the topological structure of the user-item interaction graph. However, these…

Information Retrieval · Computer Science 2022-11-28 Xin Zhou , Donghui Lin , Yong Liu , Chunyan Miao

Graph Convolutional Networks (GCN) are Graph Neural Networks where the convolutions are applied over a graph. In contrast to Convolutional Neural Networks, GCN's are designed to perform inference on graphs, where the number of nodes can…

Machine Learning · Computer Science 2024-06-12 Adrian Moldovan , Angel Caţaron , Răzvan Andonie

With the increasing use of Graph Neural Networks (GNNs) in critical real-world applications, several post hoc explanation methods have been proposed to understand their predictions. However, there has been no work in generating explanations…

Machine Learning · Computer Science 2022-12-02 Valentina Giunchiglia , Chirag Varun Shukla , Guadalupe Gonzalez , Chirag Agarwal

Graph Neural Networks (GNNs) have emerged as a cornerstone of deep learning, with most existing methods rooted in graph signal processing and diffusion equations to model message passing. However, these approaches inherently suffer from the…

Machine Learning · Computer Science 2026-05-26 Zexing Zhao , Guangsi Shi , Yu Gong , Tianyu Wang , Shirui Pan , Hongye Cheng , Yuxiao Li

In this paper, we explore the approximation theory of functions defined on graphs. Our study builds upon the approximation results derived from the $K$-functional. We establish a theoretical framework to assess the lower bounds of…

Machine Learning · Computer Science 2024-08-06 Guangrui Yang , Jianfei Li , Ming Li , Han Feng , Ding-Xuan Zhou

Graph Neural Networks (GNNs) typically operate by message-passing, where the state of a node is updated based on the information received from its neighbours. Most message-passing models act as graph convolutions, where features are mixed…

Message passing is the core operation in graph neural networks, where each node updates its embeddings by aggregating information from its neighbors. However, in deep architectures, this process often leads to diminished expressiveness. A…

Machine Learning · Computer Science 2025-11-11 Mohammad Shirzadi , Ali Safarpoor Dehkordi , Ahad N. Zehmakan

Our study reveals new theoretical insights into over-smoothing and feature over-correlation in graph neural networks. Specifically, we demonstrate that with increased depth, node representations become dominated by a low-dimensional…

Machine Learning · Computer Science 2024-09-19 Andreas Roth , Thomas Liebig

Since its inception in "Attention Is All You Need", transformer architecture has led to revolutionary advancements in NLP. The attention layer within the transformer admits a sequence of input tokens $X$ and makes them interact through…

Machine Learning · Computer Science 2024-02-23 Davoud Ataee Tarzanagh , Yingcong Li , Christos Thrampoulidis , Samet Oymak

Oversmoothing is a common phenomenon observed in graph neural networks (GNNs), in which an increase in the network depth leads to a deterioration in their performance. Graph contrastive learning (GCL) is emerging as a promising way of…

Machine Learning · Computer Science 2024-02-26 Jintang Li , Wangbin Sun , Ruofan Wu , Yuchang Zhu , Liang Chen , Zibin Zheng

Linearized Graph Neural Networks (GNNs) have attracted great attention in recent years for graph representation learning. Compared with nonlinear Graph Neural Network (GNN) models, linearized GNNs are much more time-efficient and can…

Machine Learning · Computer Science 2023-02-02 Yulin Zhu , Xing Ai , Qimai Li , Xiao-Ming Wu , Kai Zhou

Oversmoothing in Graph Neural Networks (GNNs) poses a significant challenge as network depth increases, leading to homogenized node representations and a loss of expressiveness. In this work, we approach the oversmoothing problem from a…

Machine Learning · Computer Science 2024-12-11 Biswadeep Chakraborty , Harshit Kumar , Saibal Mukhopadhyay
‹ Prev 1 3 4 5 6 7 10 Next ›